wassermanproductions/motion-previs-studio: Open-source desktop app for AI-film motion, depth, pose, and camera-move previsualization.
Open-source desktop app for AI-film motion, depth, pose, and camera-move previsualization.
Repositories
Hemanthk-source/generative-ai-for-smart-business-automation: generative-ai-for-smart-business-automation
generative-ai-for-smart-business-automation
Pengkun-ZHU/DeepLearningCompanion: A companion repository for Deep Learning (Goodfellow, Bengio & Courville), connecting mathematical theory with PyTorch implementation, CUDA optimization, and framework internals.
A companion repository for Deep Learning (Goodfellow, Bengio & Courville), connecting mathematical theory with PyTorch implementation, CUDA optimization, and framework internals.
oxbshw/watch-skill: Give any AI agent the ability to watch video — and to watch its own work and fix it. MCP + CLI + REST; scene-aware frames, OCR, local-first transcription, persistent index, and THE LOOP.
Give any AI agent the ability to watch video — and to watch its own work and fix it. MCP + CLI + REST; scene-aware frames, OCR, local-first transcription, persistent index, and THE...
eli-labz/Cognitive-Core-Skills: A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.
A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and...
avifenesh/bw24: From-scratch Rust+CUDA LLM inference engine for RTX 5090 (sm_120a) — NVFP4, MoE, MTP speculative decoding, tuned against measured hardware limits
From-scratch Rust+CUDA LLM inference engine for RTX 5090 (sm_120a) — NVFP4, MoE, MTP speculative decoding, tuned against measured hardware limits
MaryamAmjad-Dev/Maryam-Amjad-Portfolio: Next-generation AI portfolio experience built with Next.js, TypeScript, Tailwind CSS, and Generative AI, combining modern web engineering with intelligent interactions.
Next-generation AI portfolio experience built with Next.js, TypeScript, Tailwind CSS, and Generative AI, combining modern web engineering with intelligent interactions.
AbrarRagib/ml-roadmap: The complete machine learning roadmap — from-scratch Python implementations, the math explained, tested code, and real projects.
The complete machine learning roadmap — from-scratch Python implementations, the math explained, tested code, and real projects.
generalizingai/OpenStudio: OpenStudio - an open-source AI image, video, cinema, reels and lip sync studio powered by MuAPI
OpenStudio - an open-source AI image, video, cinema, reels and lip sync studio powered by MuAPI
SauravP97/ai-engineering-primer: Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.
Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.
Parthiv0121/Diffusion_image_app: Text-to-image generator built with Streamlit and Hugging Face's Stable Diffusion pipeline — prompt in, image out.
Text-to-image generator built with Streamlit and Hugging Face's Stable Diffusion pipeline — prompt in, image out.
TheLovesOfLadyPurple/Empurple-Training-Free-Algorithm-To-enhance-Diversity-of-The-Diffusion-Distillation-Model: A Training Free Algorithm To Enhance the Diversity of Diffusion Distillation Model
A Training Free Algorithm To Enhance the Diversity of Diffusion Distillation Model
qasimriaz002/AI-BootCamp-2026-GIKI: Python Foundations for GIKI AI Boot Camp 2026 | From Python basics to NumPy, Pandas & Matplotlib for AI and Machine Learning.
Python Foundations for GIKI AI Boot Camp 2026 | From Python basics to NumPy, Pandas & Matplotlib for AI and Machine Learning.
RennAkira/spicy-monopoly: 和你的 AI 一起玩的双人棋盘小游戏 · 18+ （A two-player board game you play with your AI — dice, tiles, spicy tasks, all run by code (18+））
和你的 AI 一起玩的双人棋盘小游戏 · 18+ （A two-player board game you play with your AI — dice, tiles, spicy tasks, all run by code (18+））
minkhant1996/soemind-forge: Budget-aware AI agent content studio for creating videos, images, carousels, voiceovers, music, captions, and content calendars with consistent brand assets and cost control.
Budget-aware AI agent content studio for creating videos, images, carousels, voiceovers, music, captions, and content calendars with consistent brand assets and cost control.
simonlin1212/Vibe-Research: Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。
Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。
drowzeys/Keys-Setup-Autonomous-Self-Improving-Local-Inference-Stack: Autonomous self-improving 4x DGX Spark (GB10) stack. DSV4F-DSpark=orchestrator/router; Two-Tower NVFP4(1-GPU)=diffusion; Nemotron-3-Omni=multimodal ingest; Gemma-4-12B=LoRA trainer; Qwen3.6-27B-NVFP4=light inference; cloud=rate-limited audit. Hermes MoA routing, ~90% local, self-LoRA feedback loop.
Autonomous self-improving 4x DGX Spark (GB10) stack. DSV4F-DSpark=orchestrator/router; Two-Tower NVFP4(1-GPU)=diffusion; Nemotron-3-Omni=multimodal ingest; Gemma-4-12B=LoRA trainer...
divijbajaj7/liars-dice-rl: Liar's Dice by self-play — a Deep Reinforcement Learning teaching case study. An AI learns to bluff from scratch in PyTorch, playable in the browser.
Liar's Dice by self-play — a Deep Reinforcement Learning teaching case study. An AI learns to bluff from scratch in PyTorch, playable in the browser.
Scottcjn/nemotron-twotower-cpu: Run NVIDIA Nemotron TwoTower (diffusion LLM) on any CPU: ppc64le, arm64, x86_64. No NVIDIA GPU.
Run NVIDIA Nemotron TwoTower (diffusion LLM) on any CPU: ppc64le, arm64, x86_64. No NVIDIA GPU.
drowzeys/Keys-NVIDIA-Two-Tower-Diffusion--dual-dgx-spark: keys-Nvidia — TRUE Two-Tower diffusion, NVFP4 APPLIED: Nemotron-Labs-TwoTower-30B split across two DGX Sparks over 200G fabric; NVFP4 experts + grouped Triton W4A16 GEMM = 38.9 tok/s, beats AR 1.4-1.8x.
keys-Nvidia — TRUE Two-Tower diffusion, NVFP4 APPLIED: Nemotron-Labs-TwoTower-30B split across two DGX Sparks over 200G fabric; NVFP4 experts + grouped Triton W4A16 GEMM = 38.9 tok...
matteo-grella/fucina: CPU-first tensor/autograd runtime and LLM inference engine in pure Zig — eager execution, GGUF in and out, LoRA training on CPU, benchmarked pairwise against llama.cpp.
CPU-first tensor/autograd runtime and LLM inference engine in pure Zig — eager execution, GGUF in and out, LoRA training on CPU, benchmarked pairwise against llama.cpp.
wecanmoove/azure-openai: On Azure, create generative Ai with openai
On Azure, create generative Ai with openai
Leo1998-Lu/ai-paper2slide-skill: Conference-Grade Paper-to-Slide Generation for AI Research.
Conference-Grade Paper-to-Slide Generation for AI Research.